final project

meteorite_data <- read.csv("meteorite-landings.csv")

meteorite_data <- meteorite_data %>% 
  clean_names() %>%
  filter(year >= 1900 & year <= 2013) %>% 
  select(-fall)

meteorite_data_cleaned <- meteorite_data %>%
  filter(!is.na(reclat) & !is.na(reclong)) %>%
  filter(!is.na(mass) & !is.na(year))

summary(meteorite_data_cleaned)

##      name                 id          nametype           recclass        
##  Length:37408       Min.   :    2   Length:37408       Length:37408      
##  Class :character   1st Qu.:10892   Class :character   Class :character  
##  Mode  :character   Median :21902   Mode  :character   Mode  :character  
##                     Mean   :25552                                        
##                     3rd Qu.:40134                                        
##                     Max.   :57458                                        
##       mass               year          reclat          reclong       
##  Min.   :       0   Min.   :1900   Min.   :-87.37   Min.   :-165.43  
##  1st Qu.:       6   1st Qu.:1986   1st Qu.:-76.72   1st Qu.:   0.00  
##  Median :      28   Median :1996   Median :-71.50   Median :  35.67  
##  Mean   :    7214   Mean   :1993   Mean   :-40.93   Mean   :  62.66  
##  3rd Qu.:     167   3rd Qu.:2003   3rd Qu.:  0.00   3rd Qu.: 157.17  
##  Max.   :60000000   Max.   :2013   Max.   : 81.17   Max.   : 178.20  
##  geo_location      
##  Length:37408      
##  Class :character  
##  Mode  :character  
##                    
##                    
## 

world_map <- map_data("world")
ggplot() +
  geom_map(data = world_map, map = world_map, aes(x = long, y = lat, map_id = region), fill = "white", color = "gray") +
  geom_point(data = meteorite_data, aes(x = reclong, y = reclat), color = "blue", alpha = 0.5, size = 1) +
  labs(title = "Global Distribution of Meteorite Landings (1399-2013)",
       x = "Longitude", y = "Latitude")

ggplot(meteorite_data, aes(x = recclass, y = mass)) +
  geom_jitter(width = 0.2, height = 0, alpha = 0.5) +
  scale_y_log10() +
  labs(title = "Meteorite Mass by Type",
       x = "Meteorite Type (recclass)", y = "Mass (log scale)") +
  theme(axis.text.x = element_text(angle = 90, hjust = 1))

# Count meteorite landings by year
yearly_landings <- meteorite_data %>%
  group_by(year) %>%
  summarise(count = n())

# Line plot of meteorite landings over the years
ggplot(yearly_landings, aes(x = year, y = count)) +
  geom_line(color = "blue") +
  labs(title = "Meteorite Landings Over Time",
       x = "Year", y = "Number of Meteorite Landings")

fig <- plot_ly(
  data = meteorite_data,
  type = 'scattermapbox',
  lat = ~reclat,
  lon = ~reclong,
  mode = 'markers',
  marker = list(size = 4, color = 'blue', opacity = 0.5),
  text = ~paste("Name:", name, "<br>Year:", year, "<br>Mass:", mass)
)

fig <- fig %>%
  layout(
    title = 'Global Distribution of Meteorite Landings (1399-2013)',
    mapbox = list(
      style = "carto-positron",
      zoom = 1
    )
  )

fig

yearly_landings <- meteorite_data %>%
  group_by(year) %>%
  summarise(count = n())

# Line plot with Plotly
fig <- plot_ly(
  data = yearly_landings,
  x = ~year,
  y = ~count,
  type = 'scatter',
  mode = 'lines',
  line = list(color = 'blue')
) %>%
  layout(
    title = 'Meteorite Landings Over Time',
    xaxis = list(title = 'Year'),
    yaxis = list(title = 'Number of Meteorite Landings')
  )

fig